Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    jax
    -0.07
    _broadcast
    -0.07
     ju
    -0.07
    Jer
    -0.07
     bag
    -0.06
     bull
    -0.06
    toy
    -0.06
     questioning
    -0.06
    _c
    -0.06
    _compiler
    -0.06
    POSITIVE LOGITS
     {?>↵
    0.07
     }];↵
    0.07
     })();↵
    0.07
    "}↵↵
    0.06
     })↵↵↵
    0.06
     půj
    0.06
     براى
    0.06
    			↵			↵
    0.06
     ]
↵
    0.06
    %↵↵
    0.06
    Act Density 0.053%

    No Known Activations